Skip to main content
Glama

agentic_coordinator_decompose

Break down GitHub development tasks into structured workflows by analyzing issues, decomposing requirements, and selecting appropriate agents for automated code generation and review processes.

Instructions

CoordinatorAgent実行 - タスク分解(DAG構築)・Agent選定

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
descriptionYesタスク詳細
issue_numberYesGitHub Issue番号
titleYesタスクタイトル

Implementation Reference

  • Handler function that triggers GitHub Actions workflow for CoordinatorAgent to decompose tasks (agentic_coordinator_decompose tool execution).
      private async handleCoordinatorDecompose(args: {
        issue_number: number;
        title: string;
        description: string;
      }) {
        try {
          await execAsync(
            `gh workflow run agentic-system.yml -f agent=coordinator -f issue_number=${args.issue_number}`,
            { cwd: process.env.GITHUB_REPOSITORY_PATH || process.cwd() }
          );
    
          return {
            content: [
              {
                type: 'text',
                text: `## 🎯 CoordinatorAgent起動
    
    **Issue**: #${args.issue_number}
    **Title**: ${args.title}
    
    ✅ タスク分解ワークフローを起動しました
    
    分解されたサブタスクは Issue #${args.issue_number} のコメントで確認できます`
              }
            ]
          };
        } catch (error) {
          return {
            content: [
              {
                type: 'text',
                text: `❌ エラー: ${error instanceof Error ? error.message : 'Unknown error'}`
              }
            ]
          };
        }
      }
  • Input schema definition for agentic_coordinator_decompose tool.
    inputSchema: {
      type: 'object',
      properties: {
        issue_number: {
          type: 'number',
          description: 'GitHub Issue番号'
        },
        title: {
          type: 'string',
          description: 'タスクタイトル'
        },
        description: {
          type: 'string',
          description: 'タスク詳細'
        }
      },
      required: ['issue_number', 'title', 'description']
    }
  • server.ts:126-147 (registration)
    Tool registration in TOOLS array including name, description, and schema.
    {
      name: 'agentic_coordinator_decompose',
      description: 'CoordinatorAgent実行 - タスク分解(DAG構築)・Agent選定',
      inputSchema: {
        type: 'object',
        properties: {
          issue_number: {
            type: 'number',
            description: 'GitHub Issue番号'
          },
          title: {
            type: 'string',
            description: 'タスクタイトル'
          },
          description: {
            type: 'string',
            description: 'タスク詳細'
          }
        },
        required: ['issue_number', 'title', 'description']
      }
    },
  • server.ts:238-240 (registration)
    Switch case registration mapping tool name to handler in CallToolRequestSchema handler.
    case 'agentic_coordinator_decompose':
      return await this.handleCoordinatorDecompose(args as any);

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ShunsukeHayashi/agentic-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server